基于改进随机森林算法的汽轮机振动故障诊断研究  

Research on diagnosis for vibration faults in steam turbines using IRF algorithm

作　　者：李蔚[1] 吴懿范 毛静宇 常增军 李仲博 王方舟 LI Wei;WU Yifan;MAO Jingyu;CHANG Zengjun;LI Zhongbo;WANG Fangzhou(College of Energy Engineering,Zhejiang University,Hangzhou 310027,China;Beijing Heat Supply Company,Beijing 100020,China;Beijing Jingneng Energy Technology Research Co.,Ltd.,Beijing 100089,China)

机构地区：[1]浙江大学能源工程学院,杭州310027 [2]北京热力集团有限责任公司,北京100028 [3]北京京能能源技术研究有限责任公司,北京100089

出　　处：《浙江电力》2024年第9期107-116,共10页Zhejiang Electric Power

基　　金：国家重点研发计划(2019YFE0126000)。

摘　　要：随机森林算法具有抗噪声和计算能力强的优点,被广泛应用于旋转机械的振动故障诊断中,但在工业场景中存在样本较少、无法引入先验知识、准确度较低等问题。对此,基于层次分析思想,利用信息熵引入先验知识优化决策树,提出了基于IRF(改进随机森林算法)的汽轮机振动故障诊断方法。为验证所提方法的有效性和可靠性,采用某百万火电机组数据中心的真实运行数据集进行评估。计算结果表明,相较于经典随机森林算法,IRF能够在降低33%决策树数目的情况下具有更高的精确度和低漏报率,同时运行时间缩短至经典随机森林算法的11.4%,在火电机组实时精确振动故障诊断方面有较高的实用价值。The random forest algorithm,known for its robustness against noise and powerful computational capabili⁃ties,is widely employed in diagnosing vibration faults in rotating machinery.However,when applied in industrial settings,the algorithm encounters challenges such as limited sample sizes,the inability to integrate prior knowl⁃edge,and comparatively lower accuracy.To tackle these issues,a method for diagnosing vibration faults in steam turbines using an improved random forest(IRF)algorithm is proposed.This approach incorporates prior knowledge to optimize decision trees,utilizing analytical hierarchy process(AHP)and information entropy.Genuine opera⁃tional datasets from the data center of a million-kW thermal power plant are utilized to validate the efficacy and reli⁃ability of the proposed method.Computational findings indicate that,in comparison to the traditional random forest algorithm,IRF achieves higher accuracy and a reduced miss rate,with a 33%decrease in the number of decision trees.Moreover,the operational time is slashed to just 11.4%of that taken by the traditional random forest algo⁃rithm.These results suggest that IRF holds significant practical value for real-time,precise vibration fault diagnosis in thermal power units.

关 键 词：汽轮机 振动故障诊断 改进随机森林算法 层次分析 信息熵 

分 类 号：TM621[电气工程—电力系统及自动化] TP181[自动化与计算机技术—控制理论与控制工程]